Atlas

Benchmarks

← All benchmarks

SnorkelRevOps pass@5

Professional Work

Published pass@5 on the 200-task SnorkelRevOps release; a correlated diagnostic of the pass@1 leaderboard.

Top models (higher is better)

ModelScore
Grok 4.635.0
Kimi K331.5
Grok 4.728.1
Claude Opus 5.525.8
GLM-5.325.7
Muse Spark 1.325.5
Claude Fable 5.125.1
Claude Opus 523.9
GPT-6 Astra21.1
Gemini 3.8 Flash14.4
Loading Atlas data…